This Masters thesis is a first attempt at dealing with comparison questions in open domain question answering. Research so far has only been conducted within closed domains. While closed-domain systems assume that all the information necessary to answer a question is contained in a structured database, open-domain systems have to cope with large collections of unstructured text. The obvious advantage of open-domain systems is that they are able to deal with a wide variety of topics, while closed-domain systems can only answer questions within a limited topic area. A look at question logs on the Internet reveals that users quite frequently query the differences between two concepts, which is why an open-domain system would be most useful. This study has multiple purposes. Firstly, it provides an overview of the task of answering difference questions in open domains. And secondly, some practical experiments are carried out to investigate the difficulty of carrying out the first step in answering difference questions, namely to identify the senses of the question terms. Although this represents only a small step towards a full implementation of a difference questions system, the foundations are thus laid for further research.