Hello!
Since last Sunday I am experiencing a significant spike in server resources. 
It seems to have to do with the cron, because if I stop the tasks, everything is back to normal in a few minutes.

I haven't made any modifications to the community settings for a while so I was wondering if it must be a bug.

There are a couple of things which are likely to cause you issues here.

First of all, please ensure you run all patches, as one relates to the queue task. You can do this by visiting Support in your admin CP, where you will see "Optional patch available" under the version number

The second item is that you have tables which are not running in INNODB format. InnoDB database tables typically perform more efficiently and reliably than other database engines such as MyISAM on most modern hosts when configured correctly. It is strongly encouraged to ensure all of your database tables are using the InnoDB storage engine, and that your hosting provider has configured MySQL for InnoDB use.