Canonical Information Retrieval systems perform a ranked keyword search strategy: Given a user's one-off information need (query), a list of documents, ordered by relevance, is returned. The main limitation of that "one-fits-all" approach is that long-term user interests are neglected in the search process, implicitly assuming that they are completely independent of the user query. Actually, there are information access scenarios that cannot be solved through a straightforward matching of queries and documents, since other elements influence the relevance of the retrieved results. In these scenarios, a smart search engine could exploit information about topics of interest, stored in the user profile, to automatically tailor ranking functions to a particular user. The main contribution of this paper is an extension of the vector space retrieval model in which user profiles learned by a content-based recommender system are taken into account to modify the ranking of search results. Experimental results in a movie retrieval scenario show how promising is the approach.