In case library learning environments, learners are presented with an array of narratives that can be used to guide their problem solving. However, according to theorists, learners struggle to identify and retrieve the optimal case to solve a new problem. Given the challenges novice face during case retrieval, recommender systems can be embedded in case libraries to support the decision-making process about which case is most relevant to solve new problems. This emerging technology reports how experts' assessment of case relevancy was used to retrieve and suggest the most relevant cases for the learner as they engaged in an inquiry-based learning. Specifically, our case library learning system integrates a content-based filtering, which recommends items similar to those a user has selected based on item descriptions or other user data, and is most widely used in textual domains. Implications for practice are also discussed.