While search engines have demonstrated improvement in both speed and accuracy, the response time to queries is prohibitively long for applications that require immediate and accurate responses to search queries. Examples include identification of multimedia resources related to the subject matter of a particular class, as it is in session. This paper begins with a survey of recommendation and prediction algorithms, each of which applies a different method to predict future search activity based on the search history of a user. To address the shortcomings identified in existing techniques, we draw inspiration from bioinformatics and latent semantic indexing to propose a novel predictive approach based on local alignment and feedback-based neighborhood refinement. We validate our proposed approach with tests on real-world search data. The results support our hypothesis that a majority of users exhibit search behavior that is predictable. Modeling this behavior enables our predictive search engine to bypass the common query-response model and proactively deliver a list of resources to the user.