As usual, Conifold's arrow hits the target. I'm not aware of any philosopher of note who worked solely or mainly from a dictionary but the so-called Oxford ordinary-language philosophers of the late 1940s to 1960s believed that an examination of ordinary language could throw light on philosophical problems. J.L. Austin (1911-60), the principal figure, relied mainly on his own linguistic intuitions supplemented by those of colleagues such as Geoffrey Warnock and J.O. Urmson - though the dictionary could have played a role in their inquiries.
Austin called his method, 'linguistic phenomenology', though the label never caught on. The exact flavour of his attitude to ordinary language is captured in the following passage from 'A Plea for Excuses' :
Our common stock of words embodies all the distinctions men (sic) have found worth drawing, and the connexions they have found worth making, in the lifetimes of many generations: these surely are likely to be more numerous, more sound, because they have stood up to the long test of the survival of the fittest, and more subtle, at least in all ordinary and practical matters, than any that you are I are likely to think up in our arm-chairs of an afternoon - the most favoured alternative method. (J.L. Austin, Philosophical Papers, 3rd ed., ed. G. Warnock & J. Urmson, Oxford : Clarendon Press, 1993: 182.)
Austin did not suppose that all philosophical problems could be solved or elucidated by appeal to ordinary language. His point was that if, for example, we ask what it is to do something voluntarily, a proper first step is not to pore over the word as if it represented an isolated concept, but to see the various ways, marked out in ordinary language, in which we would say or imply that an action was not voluntary or not fully voluntary : it was an accident (I barged into you because the train jolted), it was a mistake (like making an error in arithmetic), I did it negligently (I didn't mean to do it, I just didn't take enough care) and so on and on.
Ordinary language is only an aid to reflection, to borrow Coleridge's phrase. It is not the be all and end all of philosophy but it has resources that can be of use to a philosopher.
Aristotle took a different but related view of ordinary language in his Method of Opposites (Nicomachean Ethics, Bk. V, 1:5-7, 1129a17-30). If you want to understand a word or (really) a concept, look at all the operative contrasts in ordinary language. J.R. Lucas offers the example of a 'fact':
We ask " What is it being contrasted with? Is it a fact as opposed to a fiction? Or as opposed to a theory? Or as opposed to an interpretation ? Or a question of fact as opposed to a question of law? " This in itself is enough to show that there is no one unitary concept of a fact, but rather a whole sheaf of concepts, bound together indeed, but distinct. (J.R. Lucas, 'On Not Worshipping Facts', The Philosophical Quarterly (1950-), Vol. 8, No. 31 (Apr., 1958), pp. 144-156: 145.)