Caching multimedia files at the network edge has been identified as a key technology for enhancing users’ quality- of-service (QoS), while reducing redundant transmissions over capacity-constrained backhauls. Nevertheless, in small cell net- works, the efficiency of a caching policy depends on the ability of small base stations (SBSs) to anticipate the requests from the user equipments (UEs). In this paper, we propose a collaborative filtering (CF) scheme for estimating the required backhaul usage at each SBS, by mining the cacheability of UEs’ file requests. In the proposed approach, each SBS has a two-fold objective: update the bandwidth allocation based on the estimated backhaul utilization, and, given the current bandwidth availability, identify which UEs to service. We formulate the problem as a one-to many matching game between SBSs and UEs, and we propose a novel cache-aware user association algorithm that minimizes the backhaul usage at each SBS, subject to individual QoS requirements. Simulation results, based on real-world service request logs, have shown that the proposed CF-based solution can yield significant gains in terms of backhaul efficiency and cache hit-ratio, reaching up to 25%, with a maximum gap of 9% to an optimal cache-aware association technique.