Look at people who have brain cancer, and see if it's more likely to be on the side of the head where the person uses their mobile phone. If statistically significant, then it's a much easier way to prove a link.
This link has been shown in this study http://www.ncbi.nlm.nih.gov/pubmed/15475713 for acoustic neuromas.
This doesn't mean for all brain cancer and doesn't mean it's a strong effect. But if you are studying brain cancer, you have to compare apples to apples, and this study, whilst useful doesn't prove that there is link to brain cancer it only proves that they did not find a link. A more precise study is more effective.