In the process of discovering bugs, developers can either find new or enhance existing bug reports by including user feedback. Users may not only discover bugs earlier but also add important context information or steps to reproduce when describing the problems they face. App stores allow users to give feedback on apps and developers to react to it. However, finding user feedback that matches existing bug reports is challenging. In this work, we introduce DeepMatcher, an automatic approach using state-of-the-art deep learning methods to match problem reports in app reviews to bug reports in issue trackers. We evaluate DeepMatcher with four open-source apps quantitatively and qualitatively. In our evaluation, DeepMatcher identified 167 matching bug reports for 200 problem reports with three suggestions per problem report. On average, DeepMatcher achieved a hit ratio of 0.71 and a Mean Average Precision of 0.55. For 91 problem reports, DeepMatcher did not find any matching bug report, which we analyzed manually. We qualitatively looked into the issue trackers of the studied apps and found that in 47 cases, users described a problem before developers discovered and documented it. Finally, we discuss different use cases of DeepMatcher to facilitate the bug fixing process for developers.